YOLOv2 Face Detection Hits 30fps on a K210 Chip via Custom C++ Firmware
alexcovo_eth · x · 2026-10-31
An embedded engineer got YOLOv2 face detection running on a UnitV (Kendryte K210) at over 30fps — not via the usual micropython route, but with custom C++ firmware with heavily optimized inference and image compression, a showcase of extreme edge-side optimization.
More from Infra
- Canon cuts 2026 i-line stepper plan again to 155 units, -18% vs 2025 amid China share loss — zephyr_z9 · 2026-10-31
- Cloudflare Durable Objects No Longer Interrupted by Deploys, Update on Hibernate — threepointone · 2026-10-31
- Google quantum chip solves in 5 minutes a task that would take 10 septillion years — acmoytoy · 2026-10-31
- Claude Code background agents burn ~$4.80/hour just writing status lines, dev calculates — arpit_bhayani · 2026-10-31
- Two weeks of agent logs: INT4 quantization triples Qwen 27B's reasoning loops at long context — Old_Ad_6033 · 2026-10-31
- Playable Environments: Millisecond Cloud Branching as the Next Test Bed for Agents — matei_zaharia · 2026-10-31